{"uid":"cap_qq_b4I9wqFA86JatDiWiT","slug":"agentdata-speech-to-text-transcription-f9a59c19","name":"AgentData Speech-to-Text Transcription","description":"Speech to text for AI agents, $0.30 per file: MP3, WAV, M4A, OGG, FLAC or WebM audio (max 5 MB, about 5 minutes) to a transcript with timed segments, detected language and optional WebVTT subtitles. One call: send a url or base64 — no upload step, no polling. No speech found means a 400 and you pay nothing. USDC on Base, no account, no API key.","url":"https://agentdata-api.sander-van-aard.workers.dev/media/transcribe?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object"},"type":{"type":"string","const":"http"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"headers":{"type":"object","additionalProperties":{"type":"string"}},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"queryParams":{"type":"object","additionalProperties":{"type":"string"}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.3","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.3/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.3","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.3","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_gohSzsxN6K6SopkJ1g2LG","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.3","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Transcribes audio files (MP3, WAV, M4A, OGG, FLAC, WebM) into text with timed segments, detected language, and optional WebVTT subtitles, paid per-call in USDC on Base.","exampleAgentPrompt":"Transcribe this audio file for me — here's the URL: https://example.com/meeting.mp3 — I need the full transcript with timed segments and the detected language.","exampleUseCases":[{"title":"Meeting recording to transcript","prompt":"I have a recording of our team standup at https://example.com/standup.wav — can you transcribe it and give me the timed segments so I know who said what and when?"},{"title":"Podcast subtitle generation","prompt":"Turn this podcast episode into WebVTT subtitles — the file is at https://cdn.mypodcast.com/episode42.mp3 and I need timed captions for accessibility."},{"title":"Voice memo language detection","prompt":"I recorded a voice memo from a foreign-language call and saved it as base64 M4A — can you transcribe it and tell me what language is being spoken?"}],"resultDescription":"Returns a transcript with the full spoken text, timed segments (each with start/end timestamps and the corresponding text), the automatically detected language code, and optionally WebVTT subtitle content. If no speech is detected, returns a 400 error and no charge is applied.","failureModes":["No speech detected in audio — returns 400, no charge","Audio file exceeds 5 MB size limit — rejected","Unsupported audio format submitted — rejected","Audio URL unreachable or returns error — request fails","Audio duration exceeds ~5 minutes — may be rejected","Invalid base64 encoding — request fails","Insufficient USDC balance for payment — transaction fails"],"whenToPreferThis":"Choose this endpoint when you need a single synchronous call to transcribe a short audio file (up to 5 MB / ~5 minutes) without managing API keys or accounts. It is ideal for agent workflows that need timed segments and language detection together, and where you only want to pay per successful transcription. Avoid it for files larger than 5 MB, audio longer than ~5 minutes, or when you need batch/streaming transcription.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-30T06:14:29.867Z","isFirstParty":false,"canonicalSlug":"agentdata-speech-to-text-transcription-f9a59c19"}